• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.2 s.308
• /
• pp.1-11
• /
• 2006

In this paper, we propose the novel video retrieval algorithm using non-parametric based motion classification in the shot-based video indexing structure. The proposed system firstly gets the key frame and motion information from each shot segmented by scene change detection method, and then extracts visual features and non-parametric based motion information from them. Finally, we construct real-time retrieval system supporting similarity comparison of these spatio-temporal features. After the normalized motion vector fields is created from MPEG compressed stream, the extraction of non-parametric based motion feature is effectively achieved by discretizing each normalized motion vectors into various angle bins, and considering a mean, a variance, and a direction of these bins. We use the edge-based spatial descriptor to extract the visual feature in key frames. Experimental evidence shows that our algorithm outperforms other video retrieval methods for image indexing and retrieval. To index the feature vectors, we use R*-tree structures.

• Journal of Internet Computing and Services
• /
• v.3 no.2
• /
• pp.69-77
• /
• 2002

Recently, Digital video is one of the important information media delivered on the Internet and playing an increasingly important role in multimedia. This paper proposes a Video Browsing Service(VBS) that provides both the video content retrieval and the video browsing by the real-time user interface on Web, For the scene segmentation and key frame extraction of video sequence, we proposes an efficient scene change detection method that combines the RGB color histogram with the $x^2$(Chi Square) histogram. Resulting key frames are linked by both physical and logical indexing, This system involves the video editing and retrieval function of a VCR's, Three elements that are the date, the field and the subject are used for video browsing. A Video Browsing Service is implemented with MySQL, PHP and JMF under Apache Web Server.

• Journal of KIISE:Software and Applications
• /
• v.29 no.4
• /
• pp.235-247
• /
• 2002

For an efficient indexing and retrieval of digital video data, research on video caption extraction and recognition is required. This paper proposes methods for extracting artificial captions from video data and enhancing their image quality for an accurate Hangul and English character recognition. In the proposed methods, we first find locations of beginning and ending frames of the same caption contents and combine those multiple frames in each group by logical operation to remove background noises. During this process an evaluation is performed for detecting the integrated results with different caption images. After the multiple video frames are integrated, four different image enhancement techniques are applied to the image: resolution enhancement, contrast enhancement, stroke-based binarization, and morphological smoothing operations. By applying these operations to the video frames we can even improve the image quality of phonemes with complex strokes. Finding the beginning and ending locations of the frames with the same caption contents can be effectively used for the digital video indexing and browsing. We have tested the proposed methods with the video caption images containing both Hangul and English characters from cinema, and obtained the improved results of the character recognition.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.5B
• /
• pp.913-924
• /
• 2000

This paper proposes an efficient descriptor for objects motion trajectory and a video retrieval algorithm based on objects motion trajectory. The algorithm describes parameters with coefficients of 2-order polynomial for objects motion trajectory after segmentation of the object from the scene. The algorithm also identifies types, intervals, and magnitude of global motion caused by camera motion and indexes them with 6-affine parameters. This paper implements content-based video retrieval using similarity-match between indexed parameters and queried ones for objects motion trajectory. The proposed algorithm will support not only faster retrieval for general videos but efficient operation for unmanned video surveillance system.

• Journal of Information Management
• /
• v.37 no.4
• /
• pp.93-104
• /
• 2006

With the advancement of internet and video compression technology, there has been an increasing demand for video, and producted a large quantity contents of UCC. Therefore, Semantic-sensitive retrieval and construction for digital video library is more in demand than ever. However, it is extremely difficult to categorize and label scenes in any video automatically for searching wanted scene. This study proposes a method to extract certain scenes and analyze the video content, and shows the experimental results after categorizing 5 sports news(soccer, baseball, golf, basketball, and volleyball).

• Journal of Korea Multimedia Society
• /
• v.2 no.3
• /
• pp.243-251
• /
• 1999

In this paper, we suggest a novel method which defines index for effectively searching MPEG video data. The traditional methods are slow because they rely on pattern matching of images between extracted shots and user's querying images. Whereas, our method uses a different approach: It transforms images of extracted PFrames into codes and uses the codes for creating index keys. To be specific, we define five features of non-context description for transparency about user's querying.

• Journal of the Korean Society for information Management
• /
• v.24 no.4
• /
• pp.53-72
• /
• 2007

This study is designed to assess whether storyboard surrogates are useful enough to be utilized for indexing sources as well as for metadata elements using 12 sample videos and 14 participants. Study shows that first, the match rates of index terms and summaries are significantly different according to video types, which means storyboard surrogates are especially useful for the type of videos of conveying their meanings mainly through images. Second, participants could assign subject keywords and summaries to digital video, sacrificing a little loss of full video clips' match rates. Moreover, the match rate of index terms (0.45) is higher than that of summaries (0.40). This means storyboard surrogates could be more useful for indexing videos rather than summarizing them. The study suggests that 1)storyboard surrogates can be used as sources for indexing and abstracting digital videos; 2) using storyboard surrogates along with other metadata elements (e.g., text-based abstracts) can be more useful for users' relevance judgement; and 3)storyboard surrogates can be utilized as match sources of image-based queries. Finally, in order to improve storyboard surrogates quality, this study proposes future studies: constructing key frame extraction algorithms and designing key frame arrangement models.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2001.11b
• /
• pp.227-232
• /
• 2001

시청자의 취향에 맞는 방송 컨텐츠를 제공하는 쌍방향 방송 서비스에 대한 요구가 증가하면서 방송용 컨텐츠의 요약, 검색, 색인 기술의 개발이 필요하게 되었다. 이런 필요에 의해 만들어진 MPEG-7 과 TV-Anytime과 같은 국제 표준들은 영상/비디오의 효율적인 내용 특징 추출 기술 및 추출된 특징을 바탕으로 멀티미디어 데이터를 검색하는 기술을 제공할 수 있다. 본 논문에서는 상위의 MPEG-7기술자들을 사용하여 골프 비디오의 내용기반 특징을 추출하고, 이들을 통합하여 골프 비디오의 구조적 내용 정보를 기술하는 요약문(Hierarchical Summary)을 생성하였다. 제안한 방법은 국제 표준으로써 그 성능을 인정받은 MPEG-7 기술자들을 사용하여 각 기술자 모듈의 정확성을 확보하고 필요에 따라 기술자 모듈의 성능을 개선하여 효율성을 높였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.04a
• /
• pp.783-786
• /
• 2002

최근 비디오 데이터의 급격한 증가에 따라 원하는 동영상 정보를 검색하고자 할 때 막대한 시간과 노력의 낭비가 생긴다. 비디오 데이터의 효율적인 관리와 검색을 위해서는 동영상 데이터의 색인이 필요하다. 일반적으로 비디오 색인을 하기 위한 시작점은 장면전환 검출이 된다. 본 논문에서는 장면 전환을 검출한 후, 검출된 장면들 간의 변화를 참조하여 계층적 구조로 설정하여 동영상의 인덱스를 생성하는 방법을 소개한다. 컷으로 검출된 장면들을 비교하는데에는 전역적인 방법과 Bipartite 매칭을 이용한 국부적인 방법이 비교되었다. 컷 사이의 비교에 국부적인 방법을 사용함으로써 씬이 잘못 구분되는 오류를 줄일 수 있었다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.04b
• /
• pp.110-112
• /
• 2000

이미지와는 달리, 비디오 데이터는 객체에 대한 움직임 정보(motion trajectory)를 가지고 있으며, 이러한 움직임 정보는 비디오 데이터만이 가지는 매우 중요한 특징으로 비디오 데이터에 대한 색인과 내용 기반 검색을 수행하는 데 있어 중요한 역할을 한다. 따라서, 본 논문에서는 비디오 데이터베이스에서 효율적인 내용기반 검색을 위해 하나의 객체에 대한 움직임 정보를 나타내는 single motion trajectory와 두 객체에 대한 움직임 정보를 나타내는 multiple motion trajectory를 위한 새로운 시공간 표현 기법을 제안한다. 아울러, 움직임 정보에 대한 사용자 질의에 대해 유사성을 측정하여 순위부여와 Time Interval을 지원하는 새로운 유사성 측정 알고리즘인 SIST와 SIMT를 제안한다.